- Conduid
- Marketplace
- #audit
MCP servers tagged audit
225 live MCP servers tagged "audit", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with audit.
Npmjs
npm registry MCP server — package intelligence, security audits, and dependency analysis for AI assistants
P3x Network
🔍 P3X Network MCP — Model Context Protocol server exposing 17 DNS, SSL, WHOIS, email deliverability, and security tools to any MCP client
Graveyard
Audit which MCP server tools your Claude Code sessions actually invoke. Server-first, surfaces dead servers and hallucinated calls.
Storefront Audit
Model Context Protocol (MCP) server exposing @xpaysh/storefront-audit's audit() function as the audit_storefront tool. Stdio transport; runs anywhere via npx. Lets Claude Desktop…
Trabecc
The gateway and governance layer for MCP. Audit, policy, and rate-limiting for AI tool calls.
Chron
Audit-grade timestamped logs for every AI conversation
Prune
Audit MCP server usage from Claude Code transcripts. Find idle servers to prune.
Ges MCP Server
GESF MCP Server - AI Compliance Assistant for GDPR, OWASP, NIST, CIS. Check compliance, generate policies, assess risks via MCP protocol.
Fullstackgtm
Open-source agentic GTM ops framework: canonical GTM data model, pluggable deterministic audits, reviewable dry-run patch plans, approval-gated write-back with conflict detection,…
Trustcard
The "npm audit" for MCP servers — a public trust card for every Model Context Protocol server.
Sigilctl
Verifiable authorization receipts for AI agents. Prove what your agents were allowed to do — and what they were denied.
Agent Config Audit
Security auditor for AI agent configurations — scans MCP servers, Claude Code settings, agents, skills and hooks for risky permissions, inline secrets, unpinned supply chains and…
Slaunt
Privacy-first MCP agent access auditor for Claude and Codex
Security Proxy
Security proxy for MCP servers — intercepts tool calls, detects prompt injection, masks PII, and writes audit logs
Premanmcp
PreMan CLI and stdio proxy for PreMan's hosted MCP server
Mcptuner
Audit, observe, and A/B test MCP servers — score tool metadata, log wire traffic, tune descriptions.
Palar
Defensive, read-only static analyzer for local MCP tool and server definition files
Sigil
Trust scanning for MCP servers: static heuristics plus behavioral evals, with signed version-pinned trust badges. The place you check before you install an MCP server.
MCP
Provingx MCP Gateway — checks every MCP tool call against an agent passport and signs a receipt for it, local or hosted servers.
Engine
WeaveKit engine — a metadata-driven headless backend runtime with Git-versioned metadata
G8e
A zero-trust execution platform that safely bridges AI agents and infrastructure without surrendering data sovereignty
Agent Runtime Security
Open-source runtime security for tool-using AI agents. Control risky actions, enforce policies, and keep audit trails for MCP and agent workflows.
TrustVector
Independent, evidence-based trust evaluations for 100+ AI models, agents, and tools.
Decision Os Min
Execution governance for AI agents: signed action-bound decisions, Hosted effect mediation, replay resistance, and evidence-scoped isolation.
Visor
Runtime policy enforcement and audit control plane for MCP tool execution. Deterministic, non-AI policy engine that intercepts MCP tools/call requests before execution.
Sello
Service-signed encrypted receipts for AI agent actions. https://sello.build/
Unwind
Deterministic security engine for AI agents. See, block, rewind, prove.
Deadweight
Audit what your coding agents silently ignore: Claude Code's CLAUDE.md, skills, sub-agents, hooks, settings, permissions and MCP, plus Cursor rules, Copilot instructions and AGENT…
Hacker Agent
hacker-agent
Clayseal Receipts
A signed record of what an agent asked for, what policy said, and what happened.
Dsh Audit Bundle
Content-addressed audit indexes across independent DeepSeek Harness evidence producers
Dsh Policy Drift Proof
Content-addressed, value-redacted policy drift evidence for DeepSeek Harness
Wuji Legion Codex
无极军团 3.0：面向 Codex 的智能工作中枢。以自然语言组织 Skill、插件与 MCP，保留白帽判断、有界执行与证据驱动进化。公开开发中。
Provio
A safety floor your AI agents can't get under: one policy for Claude Code, Codex, Gemini CLI, Cursor, Windsurf and MCP, judged by what each call will run, backstopped by the kerne…
Kreports Dart MCP
Korean financial intelligence MCP server built by a Big4 auditor. Connects DART (Korean SEC) filings to Claude via MCP protocol. 8 tools: financial snapshots, going concern scorin…
Mcprobe
Security scanner and introspection tool for MCP servers. Connect, inspect, detect injection patterns, find tool shadowing, baseline for drift. Single binary, zero dependencies, Go…
MCP
Model Context Protocol (MCP) server for PrMaat — expose your agent passport + rooms + audit proofs as tools in Claude Desktop, Claude Code, Cursor, or any MCP client.
Shield
Security audit framework for MCP servers. 17 detectors, confidence scoring, 3 scan modes, zero dependencies. pip install mcp-shield-audit
Unwind
Deterministic security engine for AI agents. See, block, rewind, prove.
Trimum
trimum — Linux AI Agent runtime (harness): daemon + pluggable agents + unified tool gateway + sandbox + tamper-evident audit
Vaerion
Open-source verification layer for AI agents — signed receipts, fail-closed policies, deterministic proof. Local-first, zero telemetry.
Leash
Keep your AI agents on a leash. API-layer policy engine for authorization, audit, and security features which includes deny-by-default, simple YAML rules, and tamper-evident logs.
Deadweight
Audit what your coding agents silently ignore: Claude Code's CLAUDE.md, skills, sub-agents, hooks, settings, permissions and MCP, plus Cursor rules, Copilot instructions and AGENT…
Governance Gateway
Governance and multi-tenancy gateway fronting agentmemory, issue trackers, a docs corpus and CI behind the Model Context Protocol — per-tenant isolation, confirmation-gated writes…
Claude Diet
See which skills, plugins, memory, and MCP configs are eating your Claude Code context — before your bill does. Local CLI, zero network calls, terminal + HTML + JSON output.
Supabase Security MCP
MCP server for Supabase security: audit, apply fixes, re-audit from any MCP client (Claude Code, Cursor, Cline).
Managed MCP Doctor
Audit Claude Code MCP governance drift, catch when allowedMcpServers no longer covers managedMcpServers (2.1.259+). CLI + JSON/SARIF for CI.
Dlx Public Kit
# DLX Public Kit DLX Phase 1 is a public evaluator kit for a thin MCP-native trust proxy. The public face is intentionally narrow: evaluators call `extract`, then `get_execution`…
Dlx Kernel
Legacy/public companion repo for DLX kernel context. The current public Phase 1 evaluation entry is dlx-public-kit, centered on a thin MCP-native trust proxy.
Nestor
Has a human checked this? Seal/serve/audit over verified-match memory — ledger, MCP, and CLI.